Publications (21)
General Multimodal Protein Design Enables DNA-Encoding of Chemistry
Jarrid Rector-Brooks, Théophile Lambert, Marta Skreta +15
Evolution is an extraordinary engine for enzymatic diversity, yet the chemistry it has explored remains a narrow slice of what DNA can encode. Deep generative models can design new…
Multi-Layer Gaussian Splatting for Immersive Anatomy Visualization
Constantin Kleinbeck, Hannah Schieber, Klaus Engel +2
In medical image visualization, path tracing of volumetric medical data like CT scans produces lifelike three-dimensional visualizations. Immersive VR displays can further enhance…
Construction of a Validated Virtual Embodiment Questionnaire
Daniel Roth, Marc Erich Latoschik
User embodiment is important for many virtual reality (VR) applications, for example, in the context of social interaction, therapy, training, or entertainment. However, there is n…
GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance
Shiyu Li, Hannah Schieber, Niklas Corell +3
Guidance for assemblable parts is a promising field for augmented reality. Augmented reality assembly guidance requires 6D object poses of target objects in real time. Especially i…
ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimation
Hannah Schieber, Shiyu Li, Niklas Corell +3
In medical and industrial domains, providing guidance for assembly processes can be critical to ensure efficiency and safety. Errors in assembly can lead to significant consequence…
Monte Carlo pathwise sensitivities for barrier options
Thomas Gerstner, Bastian Harrach, Daniel Roth
The Monte Carlo pathwise sensitivities approach is well established for smooth payoff functions. In this work, we present a new Monte Carlo algorithm that is able to calculate the…
HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios
HyunJun Jung, Guangyao Zhai, Shun-Cheng Wu +10
Estimating 6D object poses is a major challenge in 3D computer vision. Building on successful instance-level approaches, research is shifting towards category-level pose estimation…
NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing Diverse Intrinsic and Extrinsic Camera Parameters
Hannah Schieber, Fabian Deuser, Bernhard Egger +2
Novel view synthesis using neural radiance fields (NeRF) is the state-of-the-art technique for generating high-quality images from novel viewpoints. Existing methods require a prio…
Hybrid Foveated Path Tracing with Peripheral Gaussians for Immersive Anatomy
Constantin Kleinbeck, Luisa Theelke, Hannah Schieber +3
Volumetric medical imaging offers great potential for understanding complex pathologies. Yet, traditional 2D slices provide little support for interpreting spatial relationships, f…
Complementary Textures. A Novel Approach to Object Alignment in Mixed Reality
Alejandro Martin-Gomez, Alexander Winkler, Rafael de la Tijera Obert +4
Alignment between real and virtual objects is a challenging task required for the deployment of Mixed Reality (MR) into manufacturing, medical, and construction applications. To fa…
LiftNav: Path Planning via Semantic Lifting in TSDF-Guided Gaussian Splatting
Hannah Schieber, Dominik Frischmann, Victor Schaack +2
Autonomous robots in unknown indoor environments require both reliable collision avoidance and object-level understanding. Classical representations such as TSDF support safe plann…
Sonify Anything: Towards Context-Aware Sonic Interactions in AR
Laura Schütz, Sasan Matinfar, Ulrich Eck +2
In Augmented Reality (AR), virtual objects interact with real objects. However, the lack of physicality of virtual objects leads to the absence of natural sonic interactions. When…
Convergence of Milstein Brownian bridge Monte Carlo methods and stable Greeks calculation
Thomas Gerstner, Bastian Harrach, Daniel Roth
We consider the pricing and the sensitivity calculation of continuously monitored barrier options. Standard Monte Carlo algorithms work well for pricing these options. Therefore th…
CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
Hannah Schieber, Dominik Frischmann, Victor Schaack +4
Fast and efficient 3D reconstruction is essential for time-critical robotic applications such as tele-guidance and disaster response, where operators must rapidly analyze specific…
Multi-Camera AR Guidance System for Surgical Instrument Handling and Assembly: Investigating Workload and Efficiency
Shiyu Li, Julian Kreimeier, Hannah Schieber +4
The handling and assembly of instruments during surgery imposes high cognitive demands on scrub nurses, particularly when instruments are unfamiliar. We present a supporting guidan…
Supercharging Thermal Gaussian Splatting with Depth Estimation
Manoj Biswanath, Chenxin Cai, Hannah Schieber +2
Efficient and robust 3D scene representation is crucial in autonomous driving, robotics, and related fields. While RGB images provide valuable content for 3D reconstruction, other…
Semantics-Controlled Gaussian Splatting for Outdoor Scene Reconstruction and Rendering in Virtual Reality
Hannah Schieber, Jacob Young, Tobias Langlotz +2
Advancements in 3D rendering like Gaussian Splatting (GS) allow novel view synthesis and real-time rendering in virtual reality (VR). However, GS-created 3D environments are often…
Locality-Sensitive Hashing for Efficient Hard Negative Sampling in Contrastive Learning
Fabian Deuser, Philipp Hausenblas, Hannah Schieber +3
Contrastive learning is a representational learning paradigm in which a neural network maps data elements to feature vectors. It improves the feature space by forming lots with an…
Multilevel Monte Carlo learning
Thomas Gerstner, Bastian Harrach, Daniel Roth +1
In this work, we study the approximation of expected values of functional quantities on the solution of a stochastic differential equation (SDE), where we replace the Monte Carlo e…
MultiCam: On-the-fly Multi-Camera Pose Estimation Using Spatiotemporal Overlaps of Known Objects
Shiyu Li, Hannah Schieber, Kristoffer Waldow +3
Multi-camera dynamic Augmented Reality (AR) applications require a camera pose estimation to leverage individual information from each camera in one common system. This can be achi…
DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields
Nicolas Schischka, Hannah Schieber, Mert Asim Karaoglu +6
The accurate reconstruction of dynamic scenes with neural radiance fields is significantly dependent on the estimation of camera poses. Widely used structure-from-motion pipelines…